Tag
论文提出 Preference-Behavior Model (PBM)，通过逆博弈问题联合推断 LLM 的偏好与不完美决策行为参数，并在公共物品博弈等三种社会困境中评估，发现传统行为经济学偏好测量工具无法一致预测 LLM 在战略环境中的行为，而跨博弈拟合的模型则具有预测价值。
This paper introduces MoralSim to evaluate how LLM agents behave in morally charged social dilemmas where ethical actions conflict with profit incentives, finding that no model remains consistently moral and cooperation rates vary widely.
This paper presents a two-level autoresearch framework where an outer-loop AI agent autonomously optimizes inner-loop LLM policy-synthesis pipelines for multi-agent sequential social dilemmas, achieving superior performance and discovering objective-specific mechanisms like fairness under a maximin welfare objective.
This research paper identifies the 'memory curse' in LLM agents, demonstrating that expanded context windows systematically degrade cooperative behavior in multi-agent social dilemmas by eroding forward-looking intent. The authors show that targeted fine-tuning, synthetic memory sanitization, and reducing explicit Chain-of-Thought reasoning can effectively mitigate this behavioral decay.